{"id":19181718,"url":"https://github.com/kdexd/probnmn-clevr","last_synced_at":"2025-05-07T23:07:23.945Z","repository":{"id":37605901,"uuid":"186629574","full_name":"kdexd/probnmn-clevr","owner":"kdexd","description":"Code for ICML 2019 paper \"Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering\" [long-oral]","archived":false,"fork":false,"pushed_at":"2023-08-03T16:40:44.000Z","size":1675,"stargazers_count":66,"open_issues_count":4,"forks_count":12,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-05-07T23:07:17.938Z","etag":null,"topics":["clevr","icml","icml-2019","neural-module-networks","probabilistic-models","vqa"],"latest_commit_sha":null,"homepage":"https://kdexd.github.io/probnmn-clevr","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kdexd.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2019-05-14T13:35:08.000Z","updated_at":"2024-04-22T16:13:49.000Z","dependencies_parsed_at":"2025-04-21T09:48:23.383Z","dependency_job_id":null,"html_url":"https://github.com/kdexd/probnmn-clevr","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kdexd%2Fprobnmn-clevr","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kdexd%2Fprobnmn-clevr/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kdexd%2Fprobnmn-clevr/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kdexd%2Fprobnmn-clevr/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kdexd","download_url":"https://codeload.github.com/kdexd/probnmn-clevr/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252968118,"owners_count":21833251,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["clevr","icml","icml-2019","neural-module-networks","probabilistic-models","vqa"],"created_at":"2024-11-09T10:54:21.262Z","updated_at":"2025-05-07T23:07:23.915Z","avatar_url":"https://github.com/kdexd.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"Probabilistic Neural-symbolic Models\n====================================\n\nCode for our ICML 2019 paper:\n\n**[Probabilistic Neural-Symbolic Models for Interpretable Visual Question Answering][1]**  \nRamakrishna Vedantam, Karan Desai, Stefan Lee, Marcus Rohrbach, Dhruv Batra, Devi Parikh\n\nCheckout our package documentation at\n[kdexd.github.io/probnmn-clevr](https://kdexd.github.io/probnmn-clevr)!\n\n![probnmn-model](docs/_static/probnmn_model.jpg)\n\nIf you find this code useful, please consider citing:\n\n```text\n@inproceedings{vedantam2019probabilistic,\n  title={Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering},\n  author={Ramakrishna Vedantam and Karan Desai and Stefan Lee and Marcus Rohrbach and Dhruv Batra and Devi Parikh},\n  booktitle={ICML},\n  year={2019}\n}\n```\n\nUsage Instructions\n------------------\n\n1. [How to setup this codebase?][2]\n2. [How to train your ProbNMN?][3]\n3. [How to evaluate or run inference?][4]\n\n\nPre-trained Checkpoint\n----------------------\n\nPre-trained checkpoints and corresponding config files (with all the\nhyper-parameters) for all training phases is available with v1.0 release of\nthis repository. Check out the [Releases](https://github.com/kdexd/probnmn-clevr/releases)!\n\n\nAcknowledgments\n---------------\n\nWe thank the developers of:\n\n1. [@davidmascharka/tbd-nets](https://www.github.com/davidmascharka/tbd-nets)\n   for providing a very clean implementation of our core Neural Module Network.\n\n2. [@allenai/allennlp](https://www.github.com/allenai/allennlp) for providing\n   an awesome framework which indeed takes _masking and padding seriously._ \n\n3. [@rbgirshick/yacs](https://www.github.com/rbgirshick/yacs) for providing an\n   efficient package-wide configuration management.\n\n4. [@pytorch/pytorch](https://www.github.com/pytorch/pytorch), this needs no\n   reason.\n\n\n[1]: https://arxiv.org/abs/1902.07864\n[2]: https://kdexd.github.io/probnmn-clevr/probnmn/usage/setup_dependencies.html\n[3]: https://kdexd.github.io/probnmn-clevr/probnmn/usage/training.html\n[4]: https://kdexd.github.io/probnmn-clevr/probnmn/usage/evaluation_inference.html\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkdexd%2Fprobnmn-clevr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkdexd%2Fprobnmn-clevr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkdexd%2Fprobnmn-clevr/lists"}